A5020502914- Machine Learning in Materials Science
- Transportation and Mobility Innovations
- Vehicle Routing Optimization Methods
- Reinforcement Learning in Robotics
- Video Surveillance and Tracking Methods
- Fuel Cells and Related Materials
- Membrane Separation Technologies
- Topic Modeling
- Image and Video Quality Assessment
- Autonomous Vehicle Technology and Safety
- Video Analysis and Summarization
- Molecular Junctions and Nanostructures
- Advanced Neural Network Applications
- Microgrid Control and Optimization
- Electron and X-Ray Spectroscopy Techniques
- Chemical Synthesis and Analysis
- Ferroelectric and Negative Capacitance Devices
- Surface Chemistry and Catalysis
- Robotic Path Planning Algorithms
- Electric Vehicles and Infrastructure
- Multimodal Machine Learning Applications
- Membrane-based Ion Separation Techniques
- Advanced Memory and Neural Computing
- Membrane Separation and Gas Transport
- Biomedical Text Mining and Ontologies
National University of Singapore
2021-2024
Institute of Biomedical Science
2024
University of Oxford
2024
Tsinghua University
2024
University of Electronic Science and Technology of China
2024
Membrane technologies are becoming increasingly versatile and helpful today for sustainable development. Machine Learning (ML), an essential branch of artificial intelligence (AI), has substantially impacted the research development norm new materials energy environment. This review provides overview perspectives on ML methodologies their applications in membrane design discovery. A brief is first provided with current bottlenecks potential solutions. Through applications-based perspective...
This paper presents a study on the integration of domain-specific knowledge in prompt engineering to enhance performance large language models (LLMs) scientific domains. The proposed domain-knowledge embedded method outperforms traditional strategies various metrics, including capability, accuracy, F1 score, and hallucination drop. effectiveness is demonstrated through case studies complex materials MacMillan catalyst, paclitaxel, lithium cobalt oxide. results suggest that prompts can guide...
Designing polymeric membranes with high solute-solute selectivity and permeance is important but technically challenging. Existing industrial interfacial polymerization (IP) process to fabricate polyamide-based largely empirical, which requires enormous trial-and-error experimentations identify optimal fabrication conditions from a wide candidate space for separating given solute pair. Herein, we developed novel multitask machine learning (ML) model based on an artificial neural network...
Multi-agent path finding (MAPF) is an indispensable component of large-scale robot deployments in numerous domains ranging from airport management to warehouse automation. In particular, this work addresses lifelong MAPF (LMAPF) - online variant the problem where agents are immediately assigned a new goal upon reaching their current one dense and highly structured environments, typical real-world operations. Effectively solving LMAPF such environments requires expensive coordination between...
Diverse and large-high-quality data are essential to the deep learning algorithms for autonomous driving. However, manual collection in intricate traffic scenarios is expensive, time-consuming, hard meet requirements of quantity quality. Though some generative methods have been used image synthesis editing tackle problem collection, impact object relationships on diversity frequently disregarded these approaches. In this paper, we focus occluded pedestrians within complex driving scenes...
Observing chemical reactions in complex structures such as zeolites involves a major challenge precisely capturing single-molecule behavior at ultra-high spatial resolutions. To address this, sophisticated deep learning framework tailored has been developed for integrated Differential Phase Contrast Scanning Transmission Electron Microscopy (iDPC-STEM) imaging under low-dose conditions. The utilizes denoising super-resolution model (Denoising Inference Variational Autoencoder...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Occupancy prediction has attracted intensive attention and shown great superiority in the development of autonomous driving systems. The fine-grained environmental representation brought by occupancy terms both geometry semantic information facilitated general perception safe planning under open scenarios. However, it also brings high computation costs heavy parameters existing works that utilize voxel-based 3d dense Transformer-based quadratic attention. To address these challenges, this...